top of page
About Me
Merna Alghannam
Hi, I’m Merna! I love building systems that help people connect, understand each other, and feel seen. I’ve worked across machine learning, psychology research, sarcasm interpretation, recommender design, and AI/Data Security, but the thread running through all my work is the same: I care about how technology affects people.
I’m drawn to questions like how emotion shifts across languages and how algorithms shape what we believe. More than anything, I want to build tools that feel human, systems that soften communication instead of narrowing it, and technology that makes understanding just a little easier.
Tools & Programming Languages
The tools below reflect the technologies I’ve worked with across ML, NLP, data engineering, web development, and AI security
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.jpeg)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
Experience
Cybersecurity Analyst (Jan 2024 - present)
Saudi Aramco
Research Assistant - Quantitative Psychology Lab (June 2023 - June 2024)
Boston University
Software Engineer Intern - Recommender System Infrastucture (Jun 2020–Sept 2022)
Snap Inc.
Research Intern - AI Safety (Jul 2021–May 2022)
Boston University
Software Engineer Intern - Data Engineering Tools (Jun 2020–Aug 2020)
BitSight
Projects
Welcome to my portfolio. Here you’ll find a selection of my work. Explore my projects to learn more about what I do.
ALS Resource Web App — Enhancing Access, Understanding, and Care Equity (Date: June 2023)
The ALS Resource App is a clinical decision-support tool designed to broaden patient access to treatment pathways and evolving research. Many individuals diagnosed with ALS are presented with limited care options despite the existence of numerous emerging methodologies; this platform addresses that gap by centralizing information and guiding users toward personalized recommendations through a structured, question-based flow.
Impact & Purpose
- Expands patient and clinician visibility into a wider range of treatment opportunities
- Supports informed decision-making through clear, accessible presentation of clinical options
- Encourages collaborative dialogue between patients and healthcare professionals
- Reduces knowledge disparities for individuals without access to specialized ALS care centers
By transforming fragmented information into an organized, guided experience, this tool enables patients to better advocate for themselves and clinicians to make more confident, evidence-supported decisions.
Its purpose is not only to inform — but to give direction, dignity, and agency to those navigating an unpredictable condition.
Impact & Purpose
- Expands patient and clinician visibility into a wider range of treatment opportunities
- Supports informed decision-making through clear, accessible presentation of clinical options
- Encourages collaborative dialogue between patients and healthcare professionals
- Reduces knowledge disparities for individuals without access to specialized ALS care centers
By transforming fragmented information into an organized, guided experience, this tool enables patients to better advocate for themselves and clinicians to make more confident, evidence-supported decisions.
Its purpose is not only to inform — but to give direction, dignity, and agency to those navigating an unpredictable condition.
An Analysis of Covid-Era Evictions for Massachusetts (Date: Dec 2021)
This project analyzed residential eviction filings across Massachusetts during 2020 to 2021 using court docket records combined with census demographic and economic data. The objective was to identify filing patterns, compare rates across municipalities, and evaluate how policy changes such as state and federal moratorium periods corresponded to changes in filing volume. We measured filings relative to rental households, compared geographic variation, and identified consistently higher activity in several Gateway Cities.
Analysis showed that eviction rates were not uniform across the state. Communities with higher concentrations of renters and lower median income experienced more filings per rented unit. These results were compiled to support evidence-based housing discussions, including rent-relief program design and post-moratorium stability planning.
Analysis showed that eviction rates were not uniform across the state. Communities with higher concentrations of renters and lower median income experienced more filings per rented unit. These results were compiled to support evidence-based housing discussions, including rent-relief program design and post-moratorium stability planning.
Sarcasm Detection in Autism Forum Data (Oct 2023)
The primary goal of this project is to better understand how autistic individuals perceive, interpret, and use sarcasm within online communities. Many autistic people report difficulty identifying sarcasm in conversation, which can create misunderstanding, anxiety, and barriers to social connection. By using a Playwright-based scraper to collect large quantities of real forum interactions, this work provides researchers with a more accurate picture of how sarcasm naturally appears in lived autistic communication, rather than simulated or lab-generated samples. With this data, the research seeks to understand not only where confusion arises, but also where autistic users do successfully engage in sarcasm, humor, or irony.
After scraping, we applied BART and other LLMs to highlight portions of text where sarcasm may be present, reducing manual review time and enabling more efficient large-scale analysis. LLM evaluation remains a secondary interest, as studying where models succeed or fail in undertstaning sarcasm can help us understand how machine interpretation differs from human interpretation. These comparisons reveal where AI may struggle with tone recognition, highlight risks in automated moderation or dialogue systems.
The broader social purpose of this work is to make online spaces easier, safer, and more intuitive for autistic users. By analyzing communication patterns at scale, we can help contribute to tools or insights that improve moderation systems, reduce miscommunication, and support autistic individuals in feeling included rather than misunderstood. This project reflects a step toward technology that listens more carefully, adapts more thoughtfully, and respects the diversity of how people communicate.
After scraping, we applied BART and other LLMs to highlight portions of text where sarcasm may be present, reducing manual review time and enabling more efficient large-scale analysis. LLM evaluation remains a secondary interest, as studying where models succeed or fail in undertstaning sarcasm can help us understand how machine interpretation differs from human interpretation. These comparisons reveal where AI may struggle with tone recognition, highlight risks in automated moderation or dialogue systems.
The broader social purpose of this work is to make online spaces easier, safer, and more intuitive for autistic users. By analyzing communication patterns at scale, we can help contribute to tools or insights that improve moderation systems, reduce miscommunication, and support autistic individuals in feeling included rather than misunderstood. This project reflects a step toward technology that listens more carefully, adapts more thoughtfully, and respects the diversity of how people communicate.
WAQI – Workplace Automated Quality Inspector/Engineering Chatbot (Dec 2024)
This project showcases a chat interface displaying an engineering chatbot conversation. It also includes a website WAQI was designed with one goal: to make industrial work safer using intelligent automation rather than after-incident reaction. The platform won 1st Place at the Saudi Aramco STEP Innovation Competition, achieving top ranking among 214 participants for its potential to reduce risk, improve compliance visibility, and support workers through immediate AI-based guidance.
The system was built using ReactJS, Node.js, MongoDB, REST APIs, CNN-based PPE detection, and Meta Llama for engineering assistance. LLaMA was explicitly configured to return document citations with every answer to prevent hallucination and ensure that all safety guidance is grounded in referenced material rather than model inference. The prototype used dummy plant data to simulate real incident conditions during development, enabling system demonstration before field deployment.
Key Features
AI-Powered Safety Intelligence
• CNN-based PPE detection model with 89% accuracy
• Detects missing helmets, gloves, vests, goggles, etc.
• Flags safety violations in real-time from simulated CCTV streams
Multi-Role Web Interfaces
• Worker View – PPE check, hazard inquiry, safety steps
• Inspector View – Violations dashboard, compliance logs
• Supervisor View – Oversight analytics, review of accumulated incidents
(All users have access to the engineering chatbot)
Engineering Chatbot (Meta Llama)
• Retrieves procedures from uploaded manuals rather than fabricating answers
• Returns exact source reference links in every response
• Supports safety procedure Q&A, equipment workflows, gas-testing guidance
• Combats LLM hallucination by turning back the reference document for engineer's review
Additional Prototype Modules
• Health monitoring input simulation
• Gas detection + PI Vision preview integration
• Safety logbook + post-job digital reporting
Summary
WAQI demonstrates a future where plant safety is not only monitored — but understood, referenced, and assisted by AI. With role-based interfaces, verifiable LLM responses, and high-accuracy PPE recognition, it shows how digital safety infrastructure could evolve into something proactive, transparent, and lifesaving.homepage with navigation options for accessibility.
The system was built using ReactJS, Node.js, MongoDB, REST APIs, CNN-based PPE detection, and Meta Llama for engineering assistance. LLaMA was explicitly configured to return document citations with every answer to prevent hallucination and ensure that all safety guidance is grounded in referenced material rather than model inference. The prototype used dummy plant data to simulate real incident conditions during development, enabling system demonstration before field deployment.
Key Features
AI-Powered Safety Intelligence
• CNN-based PPE detection model with 89% accuracy
• Detects missing helmets, gloves, vests, goggles, etc.
• Flags safety violations in real-time from simulated CCTV streams
Multi-Role Web Interfaces
• Worker View – PPE check, hazard inquiry, safety steps
• Inspector View – Violations dashboard, compliance logs
• Supervisor View – Oversight analytics, review of accumulated incidents
(All users have access to the engineering chatbot)
Engineering Chatbot (Meta Llama)
• Retrieves procedures from uploaded manuals rather than fabricating answers
• Returns exact source reference links in every response
• Supports safety procedure Q&A, equipment workflows, gas-testing guidance
• Combats LLM hallucination by turning back the reference document for engineer's review
Additional Prototype Modules
• Health monitoring input simulation
• Gas detection + PI Vision preview integration
• Safety logbook + post-job digital reporting
Summary
WAQI demonstrates a future where plant safety is not only monitored — but understood, referenced, and assisted by AI. With role-based interfaces, verifiable LLM responses, and high-accuracy PPE recognition, it shows how digital safety infrastructure could evolve into something proactive, transparent, and lifesaving.homepage with navigation options for accessibility.
Predict Star Rating from Movie Review- Natural Language Processing (Oct 2021)
My first machine learning project involved building a model to predict Amazon movie review star ratings using natural language processing techniques. Working with a dataset of 1.7 million reviews, I performed text preprocessing, feature extraction, and sentiment weighting using NLTK and TextBlob, transforming raw unstructured text into meaningful input for modeling.
This project objective was to predict review ratings as accurately as possible while experimenting with different ML approaches. With 179 total entrants, my submission ranked 32nd out of 150+ active competitors, a milestone that validated my early understanding of real-world ML workflow and experimentation.
To evaluate performance, I tested and compared several models (including Random Forest, Decision Tree, and k-Nearest Neighbors (KNN) ) achieving an RMSE of 0.8. I applied K-fold cross-validation and confusion matrix evaluation to verify the model’s generalizability and reliability, gaining hands-on experience in data handling, feature engineering, tuning, and model interpretation.
This project objective was to predict review ratings as accurately as possible while experimenting with different ML approaches. With 179 total entrants, my submission ranked 32nd out of 150+ active competitors, a milestone that validated my early understanding of real-world ML workflow and experimentation.
To evaluate performance, I tested and compared several models (including Random Forest, Decision Tree, and k-Nearest Neighbors (KNN) ) achieving an RMSE of 0.8. I applied K-fold cross-validation and confusion matrix evaluation to verify the model’s generalizability and reliability, gaining hands-on experience in data handling, feature engineering, tuning, and model interpretation.
Weatherway (Date: April 2022)
Many people, especially low-income families and college students, struggle to plan trips that are both affordable and enjoyable. Cheap flights are often easy to find, but cheap flights with good weather are not.
WeatherWay addresses this challenge by helping users search for flights based on the climate they want, not just the price. The platform retrieves flight options through the Amadeus Flight Destination API, checks weather forecasts using the OpenWeather One-Call API, and filters results by user-defined preferences such as minimum temperature, rain conditions, one-way travel, and non-stop availability. All results are then sorted from the cheapest to the most expensive, making it easy to compare destination options based on both affordability and climate.
By combining travel cost with weather suitability, WeatherWay helps people discover destinations that feel enjoyable, realistic, and financially accessible. It reduces the stress of planning, allowing travelers to find warm and comfortable experiences without exceeding their budget.
WeatherWay addresses this challenge by helping users search for flights based on the climate they want, not just the price. The platform retrieves flight options through the Amadeus Flight Destination API, checks weather forecasts using the OpenWeather One-Call API, and filters results by user-defined preferences such as minimum temperature, rain conditions, one-way travel, and non-stop availability. All results are then sorted from the cheapest to the most expensive, making it easy to compare destination options based on both affordability and climate.
By combining travel cost with weather suitability, WeatherWay helps people discover destinations that feel enjoyable, realistic, and financially accessible. It reduces the stress of planning, allowing travelers to find warm and comfortable experiences without exceeding their budget.
bottom of page